Effectıveness of Williams Method in the Case of Overdispersion in Logistic Regression: Application of Financial Distress for BIST 100 Index
Abstract
In logistic regression, having higher observed variation than expected variation is called as overdispersion. Pearson chi-square and deviance goodness of statistics are used to determine overdispersion in logistic regression. Different methods can be used in the case of overdispersion where goodness of fit of the model and parameter estimations are not confidential. Williams method is widely used for overdipersion situations. In this study, logistic regression analysis was built in order to classifiy firms of BIST 100 index for financial distress. At the end of this analysis overdispersion was determined and parameters were re-estimatied by Williams method in order to detect the efficeny of the method.
Keywords
Overdispersion,Logistic Regression,Financial Distress,Factor Analysis,Williams Method
Kaynakça
- Agresti, A. (1996). Categorical Data Analysis, John Wiley & Sons Inc., New York.
- Akbulut, R. ve Rençber, Ö. F. (2015). Veri Zarflama ve Lojistik Regresyon Analizi ile Çimento İşletmelerinde Finansal Performansa Dayalı Etkinliklerin Değerlendirilmesi, Uluslararası Alanya İşletme Fakültesi Dergisi, 7(3), 123-135.
- Allison, P. D. (1999). Logistic Regression Using the SAS System: Theory and Application, SAS Institude Inc., USA.
- Alpar, R. (2011). Çok Değişkenli İstatistiksel Yöntemler, Detay Yayıncılık, 3. Baskı, Ankara.
- Altman, E. (2005). Corporate Financial Distress and Bankruptcy, Third Edition, John and Wiley & Sons Inc., New York.
- Aydın, N. ve Arı, E. (2016). Hanehalkı Otomobil Talebini Belirleyen Etkenlerin İkili Lojistik Regresyon Yöntemiyle Analizi: Türkiye Örneği, Kastomonu Üniversitesi, İ.İ.B.F. Dergisi, 12 (1), 1-22.
- Cameron, A. C. ve Trivedi, P. K. (1998). Regression Analysis of Count Data, Cambridge University Press, United Kingdom.
- Cox, R. (1983). Some Remarks on Overdispersion, Biometrika, 70 (1), 269-274.
- Czado, C. (2003). Overdispersion in Logistic Regression, Erişim:[http://www-m4.ma.tum.de/courses/GLM/lec5.pdf], Erişim Tarihi: 28.09.2016.
- Field, A. (2009). Discovering Statistics Using SPSS, Sage Publications, 3 th Edition, New York.